# Few-shot Image Classification on CIFAR-FS 5-way 1-shot

Source: [Few-shot Image Classification on CIFAR-FS 5-way 1-shot](<https://www.sota2.com/research/sota/few-shot-image-classification-on-cifar-fs-5-way-1-shot>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-02-26T05:51:51.621Z

Evaluation of 5-way, 1-shot few-shot image classification performance on the CIFAR-FS dataset, reporting mean accuracy and confidence intervals.

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

| Scope | Recorded value |
| --- | --- |
| Task | Few-shot Image Classification |
| Dataset (including any stated split) | CIFAR-FS 5-way 1-shot |
| Metric | Mean Accuracy |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 9 of 9 |
| Coverage | All results currently returned for this benchmark |

Evaluation settings may differ between results. The original papers and recorded configurations are needed to establish comparability. A shared metric name alone does not establish an identical protocol.

## Metrics

- [Mean Accuracy](<https://www.sota2.com/research/sota/few-shot-image-classification-on-cifar-fs-5-way-1-shot.md?metric=Mean%20Accuracy>): Higher is better; unit: PERCENT.

- [95% CI](<https://www.sota2.com/research/sota/few-shot-image-classification-on-cifar-fs-5-way-1-shot.md?metric=95%25%20CI>): Lower is better; unit: SCALAR.

## Recorded results

| Method | Mean Accuracy | Result date | Report paper |
| --- | --- | --- | --- |
| PT-MAP | 87.7 | Not recorded | 68fa72ba1e209131cea5833f |
| PMF | 81.1 | Not recorded | 68fa72ba1e209131cea5833f |
| SIB | 80 | Not recorded | 68fa72ba1e209131cea5833f |
| PLCM | 77.6 | Not recorded | 68fa72ba1e209131cea5833f |
| Fine-tuning | 76.6 | Not recorded | 68fa72ba1e209131cea5833f |
| FewTure | 76.1 | Not recorded | 68fa72ba1e209131cea5833f |
| ProtoNet | 73.6 | Not recorded | 68fa72ba1e209131cea5833f |
| MetaOpt-SVM | 72 | Not recorded | 68fa72ba1e209131cea5833f |
| DIPA | 65.2 | Not recorded | 68fa72ba1e209131cea5833f |

### PT-MAP

Mean Accuracy: 87.7. Result ID: 699257123a6c3148490e4a7a.

[Reporting paper](<https://www.sota2.com/research/paper/68fa72ba1e209131cea5833f.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa69301e209131cea20ae3.md>)

[Implementation](<https://github.com/yhu01/PT-MAP>)

Recorded evaluation configuration: {"Backbone":"WRN-28-10","Training strategy":"Transductive","Extra data":false,"Extra labels":true}. This record does not assert independent reproduction.

### PMF

Mean Accuracy: 81.1. Result ID: 699257123a6c3148490e4a7f.

[Reporting paper](<https://www.sota2.com/research/paper/68fa72ba1e209131cea5833f.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6c5a1e209131cea33805.md>)

[Implementation](<https://github.com/hushell/pmf_cvpr22>)

Recorded evaluation configuration: {"Backbone":"ViT-small","Training strategy":"Self-Supervised + MT","Extra data":false,"Extra labels":false}. This record does not assert independent reproduction.

### SIB

Mean Accuracy: 80. Result ID: 699257123a6c3148490e4a79.

[Reporting paper](<https://www.sota2.com/research/paper/68fa72ba1e209131cea5833f.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa676c1e209131cea1610f.md>)

[Implementation](<https://github.com/amzn/xfer>)

Recorded evaluation configuration: {"Backbone":"WRN-28-10","Training strategy":"Transductive","Extra data":false,"Extra labels":true}. This record does not assert independent reproduction.

### PLCM

Mean Accuracy: 77.6. Result ID: 699257123a6c3148490e4a7b.

[Reporting paper](<https://www.sota2.com/research/paper/68fa72ba1e209131cea5833f.md>)

Recorded evaluation configuration: {"Backbone":"ResNet12","Training strategy":"Semi-Supervised","Extra data":false,"Extra labels":true}. This record does not assert independent reproduction.

### Fine-tuning

Mean Accuracy: 76.6. Result ID: 699257123a6c3148490e4a78.

[Reporting paper](<https://www.sota2.com/research/paper/68fa72ba1e209131cea5833f.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa68891e209131cea1cc20.md>)

Recorded evaluation configuration: {"Backbone":"WRN-28-10","Training strategy":"Transductive","Extra data":false,"Extra labels":true}. This record does not assert independent reproduction.

### FewTure

Mean Accuracy: 76.1. Result ID: 699257123a6c3148490e4a7d.

[Reporting paper](<https://www.sota2.com/research/paper/68fa72ba1e209131cea5833f.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6dab1e209131cea3b5c8.md>)

Recorded evaluation configuration: {"Backbone":"ViT-small","Training strategy":"Self-Supervised","Extra data":false,"Extra labels":false}. This record does not assert independent reproduction.

### ProtoNet

Mean Accuracy: 73.6. Result ID: 699257123a6c3148490e4a7c.

[Reporting paper](<https://www.sota2.com/research/paper/68fa72ba1e209131cea5833f.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa636e1e209131ce9febd3.md>)

Recorded evaluation configuration: {"Backbone":"WRN-28-10","Training strategy":"Self-Supervised","Extra data":false,"Extra labels":false}. This record does not assert independent reproduction.

### MetaOpt-SVM

Mean Accuracy: 72. Result ID: 699257123a6c3148490e4a77.

[Reporting paper](<https://www.sota2.com/research/paper/68fa72ba1e209131cea5833f.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa65a91e209131cea0bba9.md>)

[Implementation](<https://github.com/kjunelee/MetaOptNet>)

Recorded evaluation configuration: {"Backbone":"ResNet12","Training strategy":"Inductive","Extra data":false,"Extra labels":false}. This record does not assert independent reproduction.

### DIPA

Mean Accuracy: 65.2. Result ID: 699257123a6c3148490e4a7e.

[Reporting paper](<https://www.sota2.com/research/paper/68fa72ba1e209131cea5833f.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa72ba1e209131cea5833f.md>)

[Implementation](<https://github.com/rashindrie/DIPA>)

Recorded evaluation configuration: {"Backbone":"ViT-small","Training strategy":"Self-Supervised","Extra data":false,"Extra labels":false}. This record does not assert independent reproduction.

Page 1 of 1. This is an index page, not the full collection.